Results 1 - 10 of 18,253

A fast learning algorithm for deep belief nets

by Geoffrey E. Hinton, Simon Osindero - Neural Computation , 2006
"... We show how to use “complementary priors ” to eliminate the explaining away effects that make inference difficult in densely-connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a ..."
Abstract - Cited by 970 (49 self) - Add to MetaCart
We show how to use “complementary priors ” to eliminate the explaining away effects that make inference difficult in densely-connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer

The Infinite Hidden Markov Model

by Matthew J. Beal, Zoubin Ghahramani, Carl E. Rasmussen - Machine Learning , 2002
"... We show that it is possible to extend hidden Markov models to have a countably infinite number of hidden states. By using the theory of Dirichlet processes we can implicitly integrate out the infinitely many transition parameters, leaving only three hyperparameters which can be learned from data. Th ..."
Abstract - Cited by 637 (41 self) - Add to MetaCart
We show that it is possible to extend hidden Markov models to have a countably infinite number of hidden states. By using the theory of Dirichlet processes we can implicitly integrate out the infinitely many transition parameters, leaving only three hyperparameters which can be learned from data

Coupled hidden Markov models for complex action recognition

by Matthew Brand, Nuria Oliver, Alex Pentland , 1996
"... We present algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying two-handed actions. HMMs are perhaps the most successful framework in perceptual computing for modeling and ..."
Abstract - Cited by 501 (22 self) - Add to MetaCart
We present algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying two-handed actions. HMMs are perhaps the most successful framework in perceptual computing for modeling

Representing Moving Images with Layers

by John Y.A. Wang, Edward H. Adelson , 1994
"... We describe a system for representing moving images with sets of overlapping layers. Each layer contains an intensity map that defines the additive values of each pixel, along with an alpha map that serves as a mask indicating the transparency. The layers are ordered in depth and they occlude each o ..."
Abstract - Cited by 542 (11 self) - Add to MetaCart
other in accord with the rules of compositing. Velocity maps define how the layers are to be warped over time. The layered representation is more flexible than standard image transforms and can capture many important properties of natural image sequences. We describe some methods for decomposing image

Approximation by Superpositions of a Sigmoidal Function

by G. Cybenko , 1989
"... In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set ofaffine functionals can uniformly approximate any continuous function of n real variables with support in the unit hypercube; only mild conditions are imposed on the univariate fun ..."
Abstract - Cited by 1248 (2 self) - Add to MetaCart
function. Our results settle an open question about representability in the class of single bidden layer neural networks. In particular, we show that arbitrary decision regions can be arbitrarily well approximated by continuous feedforward neural networks with only a single internal, hidden layer and any

The cascade-correlation learning architecture

by Scott E. Fahlman, Christian Lebiere - Advances in Neural Information Processing Systems 2 , 1990
"... Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks. Instead of just adjusting the weights in a network of fixed topology, Cascade-Correlation begins with a minimal network, then automatically trains and adds new hidden units one by one, creatin ..."
Abstract - Cited by 801 (6 self) - Add to MetaCart
, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights are frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The Cascade

Tor: The secondgeneration onion router,”

by Roger Dingledine - in 13th USENIX Security Symposium. Usenix, , 2004
"... Abstract We present Tor, a circuit-based low-latency anonymous communication service. This second-generation Onion Routing system addresses limitations in the original design by adding perfect forward secrecy, congestion control, directory servers, integrity checking, configurable exit policies, an ..."
Abstract - Cited by 1229 (33 self) - Add to MetaCart
, and a practical design for location-hidden services via rendezvous points. Tor works on the real-world Internet, requires no special privileges or kernel modifications, requires little synchronization or coordination between nodes, and provides a reasonable tradeoff between anonymity, usability

A distributed, developmental model of word recognition and naming

by Mark S. Seidenberg, James L. McClelland - PSYCHOLOGICAL REVIEW , 1989
"... A parallel distributed processing model of visual word recognition and pronunciation is described. The model consists of sets of orthographic and phonological units and an interlevel of hidden units. Weights on connections between units were modified during a training phase using the back-propagatio ..."
Abstract - Cited by 706 (49 self) - Add to MetaCart
, and (e) differences in performance on lexieal decision and naming tasks. The model's behavior early in the learning phase corresponds to that of children acquiring word recognition skills. Training with a smaller number of hidden units produces output characteristic of many dys-lexic readers. Naming

Maximum entropy markov models for information extraction and segmentation

by Andrew McCallum, Dayne Freitag, Fernando Pereira , 2000
"... Hidden Markov models (HMMs) are a powerful probabilistic tool for modeling sequential data, and have been applied with success to many text-related tasks, such as part-of-speech tagging, text segmentation and information extraction. In these cases, the observations are usually modeled as multinomial ..."
Abstract - Cited by 561 (18 self) - Add to MetaCart
Hidden Markov models (HMMs) are a powerful probabilistic tool for modeling sequential data, and have been applied with success to many text-related tasks, such as part-of-speech tagging, text segmentation and information extraction. In these cases, the observations are usually modeled

Toolglass and magic lenses: The see-through interface

by Eric A. Bier, Maureen C. Stone, Ken Pier, William Buxton, Tony D. Derose , 1993
"... Toolglass ™ widgets are new user interface tools that can appear, as though on a transparent sheet of glass, between an application and a traditional cursor. They can be positioned with one hand while the other positions the cursor. The widgets provide a rich and concise vocabulary for operating on ..."
Abstract - Cited by 506 (8 self) - Add to MetaCart
on application objects. These widgets may incorporate visual filters, called Magic Lens™ filters, that modify the presentation of application objects to reveal hidden information, to enhance data of interest, or to suppress distracting information. Together, these tools form a see-through interface that offers
Results 1 - 10 of 18,253